Publication

Abstract : Electric Vehicles are more beneficial to people in both financial and environmental aspects. Due to the rapid increase in Electric Vehicles, the number of Electric Vehicle Charging stations has increased, leading to a poor voltage profile on the distribution grid. Since the presence of power semiconductor devices and components inside the electric vehicle charging modules led to predominant power quality disturbance, which led to the system's additional loss and maloperation of equipment, to resolve this issue, with the help of voltage and current signals as the input data, the power quality disturbances are classified using Machine Learning algorithms. In this work, different machine learning classification models have been used, and their performances are discussed. From the simulation validation, the model that best performs for classification is the Cubic Support Vector Machine, with an accuracy score of 99.6%. Independently, the regression model, Exponential Gaussian Process Regression (GPR) model, has provided the optimal Root Mean Square Error score of 0.43814.